15 citations · 33 across the 29 of their papers we have counts for
28 papers · 1 filter
Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation
Zesong Yang, Weikai Chen, Liyuan Cui +10
Long-horizon camera-controlled video generation requires recovering previously observed content from an ever-growing visual history. Existing approaches either search historical co…
Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis
Xianhao Chen, Jiarui Hu, Yuanbo Yang +5
Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language models. Existing methods have…
Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization
Zhaopeng Cui, Jiarui Hu, Jingbo Liu +7
Indoor visual relocalization plays a critical role in emerging spatial and embodied AI applications. However, prior research was predominantly devoted to low-level vision schemes,…
MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing
Zesong Yang, Yuanhang Lei, Liyuan Cui +6
Recent advances integrate physically grounded Newtonian dynamics with neural rendering frameworks, narrowing the gap between photorealistic scene reconstruction and physics-based a…
NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field
Chong Bao, Yuan Li, Bangbang Yang +5
Recently neural implicit rendering techniques have evolved rapidly and demonstrated significant advantages in novel view synthesis and 3D scene reconstruction. However, existing ne…
GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
Jiale Shi, Jiarui Hu, Zesong Yang +3
We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale se…
Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
Dongxu Wei, Qi Xu, Zhiqi Li +6
Scene-level 3D generation has long been dominated by 2D multi-view or video diffusion models. Typically, these 2D-based approaches perform scene generation in a 2D latent space, wh…
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
Yuanhang Lei, Boming Zhao, Zesong Yang +10
Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio-temporal variability of wind, as well as the complex deformati…
LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions
Jingjing Wang, Qirui Hu, Chong Bao +4
Inverse rendering in urban scenes is pivotal for applications like autonomous driving and digital twins. Yet, it faces significant challenges due to complex illumination conditions…
AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
Xiyu Zhang, Chong Bao, Yipeng Chen +5
3D reconstruction of indoor and urban environments is a prominent research topic with various downstream applications. However, existing geometric priors for addressing low-texture…
GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments
Lin Zeng, Boming Zhao, Jiarui Hu +4
Novel view synthesis with neural models has advanced rapidly in recent years, yet adapting these models to scene changes remains an open problem. Existing methods are either labor-…
InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
Zesong Yang, Bangbang Yang, Wenqi Dong +5
Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even wi…
IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos
Yuan Li, Ziqian Bai, Feitong Tan +3
We propose a novel 3D-aware diffusion-based method for generating photorealistic talking head videos directly from a single identity image and explicit control signals (e.g., expre…
Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views
Chong Bao, Xiyu Zhang, Zehao Yu +4
Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying…
NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features
Hongjia Zhai, Boming Zhao, Hai Li +5
Recently, neural radiance fields (NeRF) have gained significant attention in the field of visual localization. However, existing NeRF-based approaches either lack geometric constra…
CFSynthesis: Controllable and Free-view 3D Human Video Synthesis
Liyuan Cui, Xiaogang Xu, Wenqi Dong +3
Human video synthesis aims to create lifelike characters in various environments, with wide applications in VR, storytelling, and content creation. While 2D diffusion-based methods…
GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction
Zesong Yang, Ru Zhang, Jiale Shi +5
Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconst…
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
Yijin Li, Yichen Shen, Zhaoyang Huang +9
Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynami…
SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality
Hongjia Zhai, Xiyu Zhang, Boming Zhao +5
Visual localization plays an important role in the applications of Augmented Reality (AR), which enable AR devices to obtain their 6-DoF pose in the pre-build map in order to rende…
BlinkTrack: Feature Tracking over 80 FPS via Events and Images
Yichen Shen, Yijin Li, Shuo Chen +5
Event cameras, known for their high temporal resolution and ability to capture asynchronous changes, have gained significant attention for their potential in feature tracking, espe…
MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds
Ziqiang Dang, Tianxing Fan, Boming Zhao +4
Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to A…
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
Boming Zhao, Yuan Li, Ziyu Sun +6
Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and roboti…
GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image
Chong Bao, Yinda Zhang, Yuan Li +6
Recently, we have witnessed the explosive growth of various volumetric representations in modeling animatable head avatars. However, due to the diversity of frameworks, there is no…
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
Jiarui Hu, Xianhao Chen, Boyin Feng +5
Recently neural radiance fields (NeRF) have been widely exploited as 3D representations for dense simultaneous localization and mapping (SLAM). Despite their notable successes in s…